Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of specific acronyms related to sports events or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the letter "W" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.75
    thood
    -0.72
    ãĥķãĤ©
    -0.68
     lim
    -0.66
    ument
    -0.66
     centr
    -0.65
    adas
    -0.62
    criptions
    -0.61
     caf
    -0.60
     tom
    -0.59
    POSITIVE LOGITS
    W
    3.43
    Ws
    2.39
    WN
    1.97
    WF
    1.95
    w
    1.89
     W
    1.88
    WI
    1.80
    WT
    1.68
    WM
    1.65
    WS
    1.65
    Act Density 0.025%

    No Known Activations